Seller agents inflate tool claims disrupting buyer choices and usage
Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine Optimization
Artificial IntelligenceComputation and LanguageMultiagent Systems
Summary
This paper finds that AI-based seller agents who create product or tool listings tend to exaggerate the capabilities of their offerings when trying to get chosen more often. This exaggeration, called toolflation, misleads buyer agents who rely on descriptions to pick tools, often causing less capable options to be selected and lowering overall success. The authors tested this effect on real-market data from Amazon and Instagram and observed significant drops in task success under certain seller behavior models. They suggest that ensuring honesty in agent listings is essential for marketplace fairness and safety.
What this means in practice
- •For marketplace operators: Identify and mitigate listing exaggeration by automated sellers to maintain accuracy in product descriptions and improve buyer satisfaction.
- •For software developers for ai sellers: Design seller agent models that balance competitiveness with truthful descriptions to prevent market distortion and preserve buyer performance.
Authors
Zhenwei Tang, Di Bai, Jintao Liu, Xidong Wu, Qianfeng Wen, Xinwu Cheng
Abstract
Agents are starting to sell to other agents. Seller agents write the listings of tools, services and products, and buyer agents read these listings when they choose what to use. We show that seller agents told only to be selected more often practice generative engine optimization on their own, and that this distorts the market for sellers and for buyers. We build tool markets from real data tools on Amazon and Instagram and run every tool on every question, so we know which tools can answer each question. Under all five production models we test, sellers rewrite their descriptions to claim more and more fields, including fields that their tools return for fewer than half of the targets. We call this process toolflation. Nothing in the market limits it, and how far it goes depends on the model, as the number of claims that contradict the sellers' own evidence differs by an order of magnitude between models. Toolflation shifts the buyers' choices between sellers, and the most capable tool loses share in seven of the ten combinations of seller model and platform. Under four models, the choices stay with capable tools and buyer agents keep their task success. Under the fifth, sellers copy one another until the descriptions no longer tell the tools apart. Buyer agents then pick tools by their position in the list, tools that answer almost nothing win a quarter to two fifths of the choices, and task success falls from 89% to about 30% on Amazon, close to random choice, and from 77% to 40% on Instagram. The sellers did only what their vendors asked, and the cost fell on buyers they never dealt with. We therefore argue that honesty toward third parties under competition is part of safety alignment, and that models should be tested as sellers before they are deployed as sellers.